{"id":"https://openalex.org/W7204176797","doi":"https://doi.org/10.48550/arxiv.2608.21714","title":"L\u00ebtzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents","display_name":"L\u00ebtzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204176797","doi":"https://doi.org/10.48550/arxiv.2608.21714"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.21714","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21714","pdf_url":"https://arxiv.org/pdf/2608.21714","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.21714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119466101","display_name":"Omar El Bachyr","orcid":"https://orcid.org/0009-0000-0257-4671","observed_orcids":["https://orcid.org/0009-0000-0257-4671"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Bachyr, Omar El","raw_affiliation_strings":["University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018702042","display_name":"Fred Philippy","orcid":"https://orcid.org/0000-0001-5842-4285","observed_orcids":["https://orcid.org/0000-0001-5842-4285"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Philippy, Fred","raw_affiliation_strings":["University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119466100","display_name":"Laura Bernardy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Bernardy, Laura Maria","raw_affiliation_strings":["University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009803558","display_name":"Saad Ezzini","orcid":"https://orcid.org/0000-0001-7657-4738","observed_orcids":["https://orcid.org/0000-0001-7657-4738"]},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ezzini, Saad","raw_affiliation_strings":["King Fahd University of Petroleum and Minerals , Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Fahd University of Petroleum and Minerals , Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040326968","display_name":"Jacques Klein","orcid":"https://orcid.org/0000-0003-4052-475X","observed_orcids":["https://orcid.org/0000-0003-4052-475X"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Klein, Jacques","raw_affiliation_strings":["University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082835974","display_name":"Tegawend\u00e9 Fran\u00e7ois Bissyand\u00e9","orcid":"https://orcid.org/0000-0001-7270-9869","observed_orcids":["https://orcid.org/0000-0001-7270-9869"]},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Bissyande, Tegawende","raw_affiliation_strings":["University of Luxembourg , Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Luxembourg , Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.47049999237060547,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.47049999237060547,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.33469998836517334,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.07289999723434448,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cross-lingual-information-retrieval","display_name":"cross-lingual information retrieval","score":0.9089999794960022},{"id":"https://openalex.org/keywords/multimodal-retrieval","display_name":"multimodal retrieval","score":0.8709999918937683},{"id":"https://openalex.org/keywords/luxembourgish","display_name":"Luxembourgish","score":0.8309999704360962},{"id":"https://openalex.org/keywords/pdf-files","display_name":"PDF documents","score":0.6349999904632568},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.7289999723434448},{"id":"https://openalex.org/keywords/multilingual-fine-tuning","display_name":"multilingual fine-tuning","score":0.9200000166893005},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7820000052452087},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7250000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275000214576721},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7221999764442444},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5049999952316284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44929999113082886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41920000314712524},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C2778315783","wikidata":"https://www.wikidata.org/wiki/Q5227240","display_name":"Data archive","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21714","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21714","pdf_url":"https://arxiv.org/pdf/2608.21714","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.21714","doi":"https://doi.org/10.48550/arxiv.2608.21714","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21714","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.21714","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21714","pdf_url":"https://arxiv.org/pdf/2608.21714","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6326759832","display_name":null,"funder_award_id":"NCER22/IS/16570468/NCER-FT","funder_id":"https://openalex.org/F4320321038","funder_display_name":"Fonds National de la Recherche Luxembourg"},{"id":"https://openalex.org/G7297640339","display_name":null,"funder_award_id":"16570468","funder_id":"https://openalex.org/F4320321038","funder_display_name":"Fonds National de la Recherche Luxembourg"}],"funders":[{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204176797.pdf","grobid_xml":"https://content.openalex.org/works/W7204176797.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7100187001","https://openalex.org/W7095677826","https://openalex.org/W2051786666","https://openalex.org/W7099031054","https://openalex.org/W4415320162","https://openalex.org/W7097123813","https://openalex.org/W7095863876","https://openalex.org/W7096341233","https://openalex.org/W7095940894","https://openalex.org/W1885943037"],"abstract_inverted_index":{"Recent":[0],"page-image":[1,84],"retrievers":[2,81,85],"such":[3],"as":[4,42],"ColPali":[5],"have":[6],"improved":[7],"retrieval":[8,33,69,139],"over":[9,34],"visually":[10,60],"rich":[11],"documents,":[12,37],"yet":[13],"little":[14],"is":[15],"known":[16],"about":[17],"how":[18],"they":[19],"behave":[20],"in":[21,47,71,96],"cross-lingual,":[22],"low-resource":[23],"settings.":[24,125],"We":[25,74,100],"introduce":[26],"L\u00ebtzCross,":[27],"a":[28],"benchmark":[29,54],"for":[30,140],"cross-lingual":[31],"page-level":[32],"Luxembourgish":[35,120,131,141],"PDF":[36],"with":[38,59,82,112],"document":[39],"pages":[40],"indexed":[41],"images":[43],"and":[44,51,67,86,104,136],"queries":[45,121],"provided":[46],"English,":[48],"French,":[49],"German,":[50],"Luxembourgish.":[52],"The":[53],"combines":[55],"text-focused":[56],"QA":[57,62],"pairs":[58],"grounded":[61],"pairs,":[63],"covering":[64],"both":[65],"textual":[66],"visual":[68],"needs":[70],"PDF-based":[72],"RAG.":[73],"use":[75],"L\u00ebtzCross":[76],"to":[77],"compare":[78],"OCR-based":[79],"text-only":[80],"ColPali-style":[83],"find":[87],"that":[88],"the":[89,115,123,127,133],"latter":[90],"perform":[91],"better":[92],"across":[93,109],"query":[94,110],"languages":[95],"this":[97],"system-level":[98],"comparison.":[99],"also":[101],"examine":[102],"single-language":[103,124],"multilingual":[105,128],"fine-tuning.":[106],"Fine-tuning":[107],"transfers":[108],"languages,":[111],"French":[113],"yielding":[114],"highest":[116],"mean":[117],"performance":[118],"on":[119],"among":[122],"In":[126],"setting,":[129],"including":[130],"gives":[132],"strongest":[134],"results":[135],"substantially":[137],"improves":[138],"queries.":[142]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}
